Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1025 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.3691. Min Range: -5.3691

Max Act: 5.3691. Min Act: -0.0000

Data Index: 1432805 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 5.3691. Min Range: -5.3691

Max Act: 4.6916. Min Act: -0.0000

Data Index: 1630854 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 5.3691. Min Range: -5.3691

Max Act: 4.8242. Min Act: -0.0000

Data Index: 1396282 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 5.3691. Min Range: -5.3691

Max Act: 4.5687. Min Act: -0.0000

Data Index: 1654760 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 5.3691. Min Range: -5.3691

Max Act: 4.6480. Min Act: -0.0000

Data Index: 1477752 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 5.3691. Min Range: -5.3691

Max Act: 4.5075. Min Act: -0.0000

Data Index: 1449641 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 5.3691. Min Range: -5.3691

Max Act: 3.7936. Min Act: -0.0000

Data Index: 1555727 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 5.3691. Min Range: -5.3691

Max Act: 3.7936. Min Act: -0.0000

Data Index: 1577849 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 5.3691. Min Range: -5.3691

Max Act: 3.5105. Min Act: -0.0000

Data Index: 1392655 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 5.3691. Min Range: -5.3691

Max Act: 3.4125. Min Act: -0.0000

Data Index: 1573781 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 5.3691. Min Range: -5.3691

Max Act: 3.2126. Min Act: -0.0000

Data Index: 1637487 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 5.3691. Min Range: -5.3691

Max Act: 3.2458. Min Act: -0.0000

Data Index: 1389075 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 5.3691. Min Range: -5.3691

Max Act: 2.8677. Min Act: -0.0000

Data Index: 1491031 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 5.3691. Min Range: -5.3691

Max Act: 2.9979. Min Act: -0.0000

Data Index: 1387160 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 5.3691. Min Range: -5.3691

Max Act: 2.8977. Min Act: -0.0000

Data Index: 1464022 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 5.3691. Min Range: -5.3691

Max Act: 2.9449. Min Act: -0.0000

Data Index: 1641826 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 5.3691. Min Range: -5.3691

Max Act: 2.7416. Min Act: -0.0000

Data Index: 1465869 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 5.3691. Min Range: -5.3691

Max Act: 2.5864. Min Act: -0.0000

Data Index: 1640692 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 5.3691. Min Range: -5.3691

Max Act: 2.7112. Min Act: -0.0000

Data Index: 1365395 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 5.3691. Min Range: -5.3691

Max Act: 2.4435. Min Act: -0.0000

Data Index: 1584675 (Python Code)

Max Activating Token Index: 43